Update README.md

README.md

@@ -261,9 +261,9 @@ Example output:
 | 1          | 28               | 540        | BF16 using PIL images |
 | 4          | 110              | 640        | BF16 using PIL images |
 | 16         | 412              | 1144       | BF16 using PIL images |
-| 1          | 19               | 540        | BF16 using torch tensor |
-| 4          | 45               | 640        | BF16 using torch tensor |
-| 16         | 135              | 1144       | BF16 using torch tensor |
+| 1          | 10               | 540        | BF16 using torch tensor |
+| 4          | 33               | 640        | BF16 using torch tensor |
+| 16         | 102              | 1144       | BF16 using torch tensor |
 
 **Notes:**
 * The model has been trained in bf16 so it is **recommended to use it in bf16**.
@@ -299,12 +299,13 @@ If you use this model in your research or project, please cite it as:
 
 This model is based on the EVA architecture ([timm/eva02_base_patch14_448.mim_in22k_ft_in22k_in1k](https://huggingface.co/timm/eva02_base_patch14_448.mim_in22k_ft_in22k_in1k)), as described in the following paper:
 
+EVA-02: A Visual Representation for Neon Genesis - https://arxiv.org/abs/2303.11331
+
 ```bibtex
-@article{fang2022eva,
-  title={EVA: Exploring the Limits of Masked Visual Representation Learning at Scale},
-  author={Fang, Yuxin and Wang, Wen and Xie, Binhui and Sun, Quan and Wu, Ledell and Wang, Xinggang and Huang, Tiejun and Wang, Xinlong and Cao, Yue},
-  journal={arXiv preprint arXiv:2211.07636},
-  year={2022},
-  url={https://arxiv.org/abs/2211.07636}
+@article{EVA02,
+  title={EVA-02: A Visual Representation for Neon Genesis},
+  author={Fang, Yuxin and Sun, Quan and Wang, Xinggang and Huang, Tiejun and Wang, Xinlong and Cao, Yue},
+  journal={arXiv preprint arXiv:2303.11331},
+  year={2023}
 }
 ```